US20050185828A1 - Device and method for fingerprint identification, and computer product - Google Patents
Device and method for fingerprint identification, and computer product Download PDFInfo
- Publication number
- US20050185828A1 US20050185828A1 US11/109,765 US10976505A US2005185828A1 US 20050185828 A1 US20050185828 A1 US 20050185828A1 US 10976505 A US10976505 A US 10976505A US 2005185828 A1 US2005185828 A1 US 2005185828A1
- Authority
- US
- United States
- Prior art keywords
- registered
- fingerprint
- fingerprint image
- registered fingerprint
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Definitions
- the present invention relates to a device and method for fingerprint identification, and a computer product that are capable of being installed in portable terminals such as a PDA (Personal Digital Assistant), a cellular phone, a PHS (Personal Handyphone System) terminal, a compact notebook-type personal computer, and the like.
- portable terminals such as a PDA (Personal Digital Assistant), a cellular phone, a PHS (Personal Handyphone System) terminal, a compact notebook-type personal computer, and the like.
- fingerprint identification devices are used to identify a person using his/her fingerprint as an image that is read by an image sensor. More specifically, at first, an image sensor reads a fingerprint of a person to be identified, and then an image of the fingerprint read is registered as a fingerprint image.
- the image sensor reads the fingerprint of the person to be identified, and a matching degree is checked between the fingerprint image and a fingerprint image previously registered. If the matching degree is equal to or more than a threshold value, then the identity of the person is authenticated.
- a pattern matching method is often used to calculate the matching degree between the two fingerprint images.
- I(x, y) and T(x, y) take the value of 0 or 1.
- the evaluation value at this time may be obtained by the expression (1) given above, or by the following expression (2).
- the expression used to perform a correlation operation is not limited thereto, but has various forms.
- v ( x, y ) (1/ A ) ⁇ not ( I ( i, j ) xor T ( i-x, j-y )) (2) where “xor” represents an exclusive OR, and “not” represents negative, and A is the overlapping area between I(i, j) and T(i-x, j-y).
- the pattern matching method used in the conventional fingerprint identification device has one significant problem. This is the overlapping area between the read fingerprint image and the registered fingerprint image.
- a factor A corresponds to the area of the overlap.
- the area needs to be divided by the factor A to normalize it.
- the factor A as a denominator reduces, which causes the value of matching degree to be inaccurate.
- the area of the overlap is required to be about a half of the fingerprint image. Therefore, to obtain the larger area of the overlap, it is effective to use an image sensor having large area. Basically, by using an image sensor larger than the area of a finger, the overlap occupies most part of the image, and the problem does not occur.
- a fingerprint identification device includes a relative position calculating unit that calculates a relative position for each of registered fingerprint images, each of which is registered for each of a plurality of parts of one finger of a person; a image acquiring unit that acquires an image of a part of a finger of a person to be identified, as a read fingerprint image; a specifying unit that specifies a registered fingerprint image from among the registered fingerprint images, based on the relative position; a matching degree calculating unit that calculates a matching degree between the read fingerprint image and the registered fingerprint image specified; and an authenticating unit that authenticates a fingerprint if the matching degree is greater than a predetermined value.
- a method of fingerprint identification includes registering a fingerprint image, as registered fingerprint images, for each of a plurality of parts of one finger of a person; calculating a relative position for each of the registered fingerprint images; acquiring an image of a part of a finger of a person to be identified, as a read fingerprint image; specifying a registered fingerprint image from among the registered fingerprint images, based on the relative position; calculating a matching degree between the registered fingerprint image specified and the read fingerprint image; executing the specifying and the calculating until the matching degree is greater than a predetermined value.
- a computer-readable recording medium stores therein a computer program that implements the above method on a computer.
- FIG. 1 is a perspective view of an exterior of a portable terminal, to which a fingerprint identification device according to the present invention is applied;
- FIG. 2 is a block diagram of an electrical configuration of the portable terminal shown in FIG. 1 ;
- FIG. 3 is a diagram of a registered fingerprint image information group that is registered in a RAM shown in FIG. 2 ;
- FIG. 4 is a diagram of a relative positional relation between various fingerprint images
- FIG. 5 is a diagram for explaining a fingerprint comparison process
- FIG. 6 is a diagram of one search area
- FIG. 7 is a diagram of a whole search area
- FIG. 8 is a diagram of the whole search area
- FIG. 9 is a diagram for explaining a fingerprint re-registration process
- FIG. 10 is a flowchart for explaining an operation of the embodiment.
- FIG. 11 is a flowchart for explaining a fingerprint registration process shown in FIG. 10 ;
- FIG. 12 is a flowchart for explaining a fingerprint comparison process shown in FIG. 10 ;
- FIG. 13 is a flowchart for explaining a fingerprint re-registration process shown in FIG. 10 .
- FIG. 1 is a perspective view of an exterior of a portable terminal 100 to which a fingerprint identification device according to one embodiment of the present invention is applied.
- FIG. 2 is a block diagram of an electrical configuration of the portable terminal 100 shown in FIG. 1 .
- the portable terminal 100 includes an information processing function and a communication function, and further includes a fingerprint registration function, a fingerprint comparison function, and a fingerprint re-registration function, etc.
- a housing 110 shown in FIG. 1 includes a display unit 150 and an image sensor 170 .
- the display unit 150 is a liquid crystal display for displaying various types of information.
- a touch panel 160 adheres to the display unit 150 .
- a stylus 190 is used to touch the touch panel 160 , and input a character and so on, like a keyboard.
- the image sensor 170 reads a fingerprint image, and has an area that is smaller than the area of a fingerprint portion of a finger, for example, 3 mm square to 10 mm square. Therefore, only a part of a fingerprint can be read in one reading by the image sensor 170 .
- a CPU 120 executes a computer program stored in a ROM (read-only memory) 130 to realize the information processing function, the communication function, the fingerprint registration function, the fingerprint comparison function, and the fingerprint re-registration function, etc.
- the ROM 130 stores the computer program and various types of data.
- a RAM (random access memory) 140 is a rewritable memory.
- a registered fingerprint image information group 200 as shown in FIG. 3 is registered in the RAM 140 .
- the registered fingerprint image information group 200 corresponds to six registered fingerprint images 230 1 to 230 6 (images of various parts of the fingerprint) that are read by the image sensor 170 six times and registered.
- the registered fingerprint image information group 200 includes registered fingerprint image information 210 1 to 210 6 , and supplementary information 220 1 to 220 6 .
- the registered fingerprint image information 210 1 to 210 6 are fingerprint image information corresponding to the registered fingerprint images 2301 to 2306 of six parts of a fingerprint 310 of a finger 300 as shown in FIG. 4 , and are read by the image sensor 170 . These registered fingerprint images 2301 to 2306 cover almost entire of the fingerprint 310 of the finger 300 , and overlap one another.
- the supplementary information 220 1 to 220 6 are correlated to the registered fingerprint image information 210 1 to 210 6 , respectively, and each of them includes information such as a registered fingerprint image number, a relative-position X coordinate, a relative-position Y coordinate, and a registered date & time.
- the registered fingerprint image number is a unique number assigned to the registered fingerprint image information (registered fingerprint image).
- the relative-position X coordinate and the relative-position Y coordinate are X coordinate and Y coordinate assuming that in the registered fingerprint images 230 1 to 230 6 , for example, a left upper point P 1 (0, 0) of the registered fingerprint image 230 1 , which is read first, is an origin.
- the X coordinate and the Y coordinate represent a relative position between the left upper point P 1 and a left upper point of another registered fingerprint image.
- the registered date & time indicates a date & time on which the registered fingerprint image information is registered in the RAM 140 .
- a communication interface 180 is an interface connected to a network (not shown) based on a predetermined communication protocol, and is used to perform communication with another portable terminal and the like.
- the image sensor 170 reads a part of the fingerprint of a person to be identified as a read fingerprint image 400 , as shown in FIG. 5 .
- the read fingerprint image 400 is assumed to correspond to a part 320 of the finger 300 .
- a registered fingerprint image 230 5 having the broadest area of an overlap with the part 320 , is selected from the registered fingerprint images 230 1 to 230 6 . Then, the value of matching degree is calculated, between the registered fingerprint image 230 5 and the read fingerprint image 400 .
- the part 320 is shifted little by little by a predetermined distance, so as to cover the whole area throughout the fingerprint 310 of the finger 300 (area obtained by slightly increasing an area of the registered fingerprint images 230 1 to 230 6 ), and the values of matching degree are calculated each time. Of all these values, the highest value of the matching degree being is regarded as the final value of matching degree.
- Such a search method allows the amount of calculation to be largely reduced as compared with a case where values of matching degree between the registered fingerprint images and the read fingerprint images are calculated in a “round robin” manner.
- a range of a margin slightly increased with respect to the registered fingerprint image is assumed as a range of which a half of the area can be shared by the read fingerprint image and the registered fingerprint image. If so, as shown in FIG. 6 , a search area of the maximum value of matching degree for one registered fingerprint image includes the registered fingerprint image 230 1 and a diagonally shaded area 240 1 . The whole search area (the registered fingerprint images 230 1 to 230 6 and diagonally shaded areas 240 1 to 240 6 ) is shown in FIG. 7 .
- the registered fingerprint image 230 1 of FIG. 6 consists of 96 pixels square.
- the diagonally shaded area 240 1 is assumed to have 23904 pixels. Therefore, the search area (the registered fingerprint image 230 1 and the diagonally shaded area 240 1 ) consists of 33120 pixels.
- the number of pixels of the whole search area is 198720 (33120 ⁇ 6) pixels.
- the whole search area in the search method as explained with reference to FIG. 5 indicates the registered fingerprint images 230 1 to 230 6 in the overlapping state and a diagonally shaded area 250 around, as shown in FIG. 8 . Therefore, this whole search area is less than the whole search area of FIG. 7 .
- the diagonally shaded area 250 shown in FIG. 8 has 42583 pixels.
- the registered fingerprint images 230 1 to 230 6 in the overlapping state have 34655 pixels.
- the whole search area as shown in FIG. 8 has 77238 (42583+34655) pixels, which is a half or less than the whole search area (198720 pixels) of FIG. 7 .
- the search method of the present invention allows reduction in the amount of calculation, because the area to be searched can be largely reduced.
- a fingerprint re-registration process is executed, in which an unnecessary registered fingerprint image is deleted and the read fingerprint image is re-registered as a new registered fingerprint image.
- a read fingerprint image 230 NEW read by the image sensor 170 matches to a large extent another registered fingerprint image at the position shown in the figure, and if the read fingerprint image 230 NEW is to be registered, then the range to be covered largely increases as compared with the registered fingerprint image 230 2 .
- One problem is that a fingerprint image of another person may be erroneously registered, and another problem is that the number of registered fingerprint images that can be stored in the RAM 140 is generally limited.
- the problem of registering another person's fingerprint image may be avoided by using a method of checking the fingerprint image twice, or a method of registering the fingerprint image when the value of matching degree is sufficiently high.
- a threshold value of 1/10,000 or a threshold value of 1/1 million may be set as a false acceptance rate.
- the fingerprint identification device is operated based on the false acceptance rate as 1/10,000, a match is determined in both of the cases. Therefore, only if the false acceptance rate is the threshold value of 1/1 million in the latter case, the read fingerprint image 230 NEW is registered.
- the whole area of the registered fingerprint image 230 3 of FIG. 9 overlaps the other registered fingerprint images.
- the other registered fingerprint images can substitute it. Therefore, to re-register a new read fingerprint image 230 NEW , any registered fingerprint image (registered fingerprint image 2303 in this case) that can be substituted with other registered fingerprint images is searched for, and is deleted. This allows increase in a range that covers the registered fingerprint images, without increase in the memory capacity of the RAM 140 in which the read fingerprint image 23 ONEW is registered.
- re-registering a registered fingerprint image it is also possible to prevent degradation in performance due to a change of a finger with time. For example, if a fingerprint image is registered when a user hurts his/her finger, the finger is getting better with the passage of time. Therefore, when the finger heals, identification may not be carried out properly.
- sequentially re-registering registered fingerprint images it is possible to perform excellent identification at any time according to the change of the finger with the passage of time.
- step SA 1 of FIG. 10 the CPU 120 (see FIG. 2 ) of the portable terminal 100 determines whether a user issues a fingerprint registration request for newly registering the registered fingerprint image information group 200 (see FIG. 3 ) in the RAM 140 , and sets the result of determination to “No” in this case.
- step SA 2 the CPU 120 determines whether there is a fingerprint identification request, and sets the result of determination to “No” in this case.
- step SA 3 the CPU 120 determines whether there is a fingerprint re-registration request, and sets the result of determination to “No” in this case. Thereafter, the CPU 120 repeats determinations at step SA 1 to step SA 3 until it is determined as Yes” at any of step SA 1 to step SA 3 .
- the CPU 120 sets the result of determination at step SA 1 to “Yes”.
- the CPU 120 executes the fingerprint registration process.
- the CPU 120 causes the display unit 150 to display “Put a finger on the sensor”, and prompts the person to be registered to put the finger on the image sensor 170 . With this prompt, the person to be registered puts the finger on the image sensor 170 .
- the image sensor 170 reads a part of the finger of the person to be registered as, for example, the registered fingerprint image 230 1 of FIG. 4 .
- the registered fingerprint image 230 1 is a binary image of white and black.
- the CPU 120 causes the display unit 150 to display “Fingerprint reading is complete. Lift the finger”, and prompts the person to be registered to lift the finger from the image sensor 170 . With this prompt, the person to be registered lifts the finger from the image sensor 170 .
- the CPU 120 determines whether it is the first time that the fingerprint image is read, and sets the result of determination to “Yes” in this case.
- a relative position coordinate XY coordinate system
- step SB 1 in the same manner as explained above, the CPU 120 causes the display unit 150 to display “Put a finger on the sensor”, and prompts the person to be registered to put the finger on the image sensor 170 . With this prompt, the person to be registered puts the finger on the image sensor 170 . In this case, because of human errors, a displacement arises between the position in which the finger is put for the first time and the position in which the finger is put for the second time.
- the image sensor 170 reads a part of the finger of the person to be registered as, for example, the registered fingerprint image 230 2 of FIG. 4 .
- the CPU 120 causes the display unit 150 to display “Fingerprint reading is complete. Lift the finger”, and prompts the person to be registered to lift the finger from the image sensor 170 . With this prompt, the person to be registered lifts the finger from the image sensor 170 .
- the CPU 120 determines whether it is the first time that the fingerprint image is read, and sets the result of determination to “No” in this case.
- the CPU 120 performs a correlation operation (the value of matching degree is calculated based on the matching pattern or the like) between the registered fingerprint image 230 2 read and each of the registered fingerprint images (in this case, only the registered fingerprint image 230 1 ) in the registered fingerprint image information group 200 (in this case, only the registered fingerprint image information 210 1 and the supplementary information 220 1 ), and calculates each value of matching degree.
- a correlation operation the value of matching degree is calculated based on the matching pattern or the like
- the CPU 120 determines the highest value of matching degree among the values of matching degree, a registered fingerprint image number of a registered fingerprint image corresponding to the highest value of matching degree, and an amount of relative positional displacement (x, y) between the two, and stores these pieces of information in the RAM 140 .
- step SB 7 the CPU 120 determines whether the highest value of matching degree obtained at step SB 6 exceeds a preset threshold value, and sets the result of determination to “Yes” in this case. If the result of determination at step SB 7 is “No”, the process at step SB 1 is executed.
- the CPU 120 calculates a relative position between the registered fingerprint image 230 1 (see FIG. 4 ) having registered fingerprint image number as 1, and the registered fingerprint image 230 2 that corresponds to the highest value of matching degree.
- a relative-position X coordinate and a relative-position Y coordinate are calculated from the relative-position X coordinate and the relative-position Y coordinate that correspond to the registered fingerprint image that matches (in this case, registered fingerprint image 230 1 ), and also from the values of relative positional displacement (x, y).
- the values of the relative-position X coordinate and the relative-position Y coordinate corresponding to the registered fingerprint image 230 1 are set as Xs and Ys
- the values of relative positional displacement (x, y) are set as Xo and Yo
- relative-position X coordinate (Xnew) and Y coordinate (Ynew) are calculated using the following expression (3).
- Xnew Xs+Xo
- Ynew Ys+Yo (3)
- step SB 10 the CPU 120 determines whether the number of registered fingerprint image information (supplementary information) registered in the RAM 140 is 6 (preset number), and sets the result of determination to “No” in this case. Thereafter, step SB 1 to step SB 4 and step SB 6 to step SB 10 are repeated, and the registered fingerprint image information 210 3 to 210 6 (supplementary information 220 3 to 220 6 ) corresponding to the registered fingerprint images 230 3 to 230 6 of FIG. 4 are sequentially registered in the RAM 140 . With this registration, the CPU 120 sets the result of determination at step SB 10 to “Yes”, and returns to the main routine of FIG. 10 . Thus, fingerprint identification is achieved.
- the CPU 120 sets the result of determination at step SA 2 of FIG. 10 to “Yes”.
- the CPU 120 executes the fingerprint comparison process.
- the CPU 120 causes the display unit 150 to display “Put a finger on the sensor”, and prompts the person to be identified to put the finger on the image sensor 170 . With this prompt, the person to be identified puts the finger on the image sensor 170 .
- the image sensor 170 reads a part of the finger of the person to be identified as, for example, the read fingerprint image 400 shown in FIG. 5 .
- the read fingerprint image 400 is a binary image of white and black.
- the CPU 120 decides a range (X, Y directions) to assume a position where the read fingerprint image 400 is present. More specifically, the X direction is a range from the smallest relative-position X coordinate to the largest relative-position X coordinate, among the six registered fingerprint images shown in FIG. 4 . On the other hand, the Y direction is a range from the smallest relative-position Y coordinate to the largest relative-position Y coordinate.
- an area to be covered by the registered fingerprint images does not always cover the whole area of the finger, and therefore, it is appropriate that the area is extended to an area where the area may overlap a half of the finger.
- the size of a fingerprint image is set to have a width XL and a length YL.
- An assumption range is expressed by the following expression (4). Range in X direction: Xmin ⁇ XL/2 to Xmax+XL/2 (4) Range in Y direction: Ymin ⁇ YL/2 to Ymax+YL/2
- the CPU 120 performs calculation on the whole assumption range based on assumption that the read fingerprint image 400 lies within that position.
- the CPU 120 when deciding a range assumed of the read fingerprint image 400 , the CPU 120 further decides one point in the range as a position assumed of the read fingerprint image 400 (coordinates of the point are set as XV, YV).
- step SC 5 when assuming that any position of the range is a position in which the read fingerprint image 400 is read, the CPU 120 determines whether there is a registered fingerprint image of which more than half area overlaps the read fingerprint image 400 .
- the overlapping area is expressed by the following expression (5) where Xn is a relative-position X coordinate and Yn is a relative-position Y coordinate.
- step SC 5 If the result of determination at step SC 5 is “No”, determination is performed at step SC 10 .
- step SC 6 the CPU 120 calculates the overlapping area using the following expression (6), and selects a registered fingerprint image in which the overlapping area S is the largest.
- S ( XL ⁇
- the CPU 120 calculates a value of matching degree between the registered fingerprint image selected at step SC 6 and the read fingerprint image 400 . More specifically, assuming the relative-position X coordinate and the relative-position Y coordinate of the registered fingerprint image selected are XS and YS, respectively, the value V of matching degree is expressed by the following expression (7).
- X sml is the larger of XS and XV
- XIar is obtained by adding XL to the smaller of XS and XV
- Y sml is the larger of YS and YV
- YIar is obtained by adding YL to the smaller of YS and YV.
- I(x, y) is a pixel value at a lower position by the coordinates x, y, from the left upper side of the read fingerprint image 400
- T(x, y) is a pixel value at a lower position by the coordinates x, y, from the left upper side of the registered fingerprint image selected.
- step SC 8 the CPU 120 determines whether the value V of matching degree calculated at step SC 7 exceeds the largest value among the values of matching degree in all the positions assumed so far, i.e., whether the value V exceeds the maximum value Vmax of matching degree. If the result of determination is “No”, determination is performed at step SC 10 .
- step SC 9 the CPU 120 substitutes the value V of matching degree in the maximum value Vmax of matching degree, to update the maximum value Vmax of matching degree.
- step SC 10 the CPU 120 determines whether values of matching degree are calculated at all the positions in the range of the position assumed of the read fingerprint image 400 , sets the result of determination to “No” in this case, and executes the process at the step SC 4 and thereafter. Step SC 4 to step SC 10 are repeated until the result of determination at step SC 10 is obtained as “Yes”.
- step SC 11 the CPU 120 determines whether the maximum value Vmax of matching degree is equal to or more than the threshold value for comparison, and sets the result of determination to “Yes” in this case.
- step SC 12 the CPU 120 determines that a match is found, and authorizes that the person to be identified is identified as the person to be registered, and returns to the main routine of FIG. 10 .
- step SC 11 determines that there is no match, determines that the person to be identified is not the person to be registered, and returns to the main routine of FIG. 10 .
- the CPU 120 Upon receiving the fingerprint re-registration request, the CPU 120 sets the result of determination at step SA 3 of FIG. 10 to “Yes”. At step SA 6 , the CPU 120 executes a fingerprint re-registration process.
- step SD 1 the CPU 120 executes the fingerprint comparison process (see FIG. 12 ) a first time.
- step SD 2 the CPU 120 determines whether a match is found as a result of comparison at step SD 1 . If the result of determination is “No”, the CPU 120 returns to the main routine of FIG. 10 .
- step SD 2 determines whether the result of determination at step SD 2 is “Yes”
- step SD 3 the CPU 120 executes the fingerprint comparison process (see FIG. 12 ) a second time.
- step SD 4 the CPU 120 determines whether a match is found as a result of comparison at step SD 3 . If the result of determination is “No”, the CPU 120 returns to the main routine of FIG. 10 .
- the fingerprint comparison process twice, it is possible to prevent unauthorized use of the device by a malicious third party, and to enhance reliability.
- step SD 5 the CPU 120 selects one registered fingerprint image information (registered fingerprint image) from the registered fingerprint image information group 200 (see FIG. 3 ).
- step SD 6 the CPU 120 secures a RAM area for checking, having the same size as the registered fingerprint image information in the RAM 140 , and initializes all the values in the RAM area for checking to 0.
- the CPU 120 uses the values of the relative position to calculate an overlapping area between the registered fingerprint image selected at step SD 5 and another registered fingerprint image, and stores the value of 1 in a portion corresponding to the position of the overlapping area in the RAM area for checking.
- the CPU 120 determines whether the value of 1 is stored in 90% or more of the RAM area for checking, and sets the result of determination to “No” in this case.
- the CPU 120 determines whether all the overlaps are checked, sets the result of determination to “No” in this case, and executes the process at step SD 5 and thereafter.
- step SD 9 If the result of determination at step SD 9 is “Yes”, the CPU 120 returns to the main routine of FIG. 10 .
- step SD 10 the CPU 120 deletes the relevant registered fingerprint image information and the supplementary information from the registered fingerprint image information group 200 .
- the CPU 120 causes the image sensor 170 to read a new fingerprint image in the same manner as explained above.
- step SD 12 the CPU 120 re-registers in the RAM 140 , new registered fingerprint image information and supplementary information that correspond to the fingerprint image, as the registered fingerprint image information group 200 .
- registered fingerprint images of the parts of one finger of a person to be registered are registered as the registered fingerprint image information group 200 .
- One registered fingerprint image is selected from a plurality of registered fingerprint images based on relative positions of the registered fingerprint images, to perform fingerprint identification based on a matching degree between the one registered fingerprint image and the read fingerprint image. Therefore, the present invention can be installed in a portable terminal having such a small-sized image sensor that reads only a part of the fingerprint of a finger, and hence, can achieve highly accurate fingerprint identification.
- the speed can be prevented from slowing.
- a method of deciding which registered fingerprint image is to be deleted upon re-registration may be changed as follows.
- a function may be provided to store a date & time related to each registered fingerprint image.
- the function stores a date & time at fingerprint identification in a part where a particular date & time of a registered fingerprint image is stored.
- the particular date & time is the one when the highest value of matching degree about the registered fingerprint image is obtained, at the time of the fingerprint identification.
- the date & time related to all the registered fingerprint images are referred to.
- the registered fingerprint image that is dated about one month or more ago is deleted, and a new fingerprint image is re-registered.
- the registered fingerprint image dated one month or more ago is not used, because there is a problem that a part of the fingerprint image may be distorted or missing.
- the date & time on which the fingerprint image is last re-registered is compared with the current date & time. If a difference between the two dates is about six months or more, all pieces of the registered fingerprint image information registered in the RAM 140 are deleted, and the person to be identified is made to re-register fingerprint images until the number of registered fingerprint images reaches a specific number of images. Based on this, all the old fingerprint images are deleted, and new fingerprint images can be re-registered, thereby improving identification performance. In this case, the registered fingerprint image is updated according to a change of a finger with the passage of time, which allows fingerprint identification with high accuracy at any time.
- the present invention can be installed even in a portable terminal having a small-sized image sensor that can read only a part of the fingerprint of a finger, and can achieve highly accurate fingerprint identification.
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
- Image Analysis (AREA)
Abstract
Description
- 1) Field of the Invention
- The present invention relates to a device and method for fingerprint identification, and a computer product that are capable of being installed in portable terminals such as a PDA (Personal Digital Assistant), a cellular phone, a PHS (Personal Handyphone System) terminal, a compact notebook-type personal computer, and the like.
- 2) Description of the Related Art
- Conventionally, fingerprint identification devices are used to identify a person using his/her fingerprint as an image that is read by an image sensor. More specifically, at first, an image sensor reads a fingerprint of a person to be identified, and then an image of the fingerprint read is registered as a fingerprint image.
- To actually identify a fingerprint, the image sensor reads the fingerprint of the person to be identified, and a matching degree is checked between the fingerprint image and a fingerprint image previously registered. If the matching degree is equal to or more than a threshold value, then the identity of the person is authenticated.
- A pattern matching method is often used to calculate the matching degree between the two fingerprint images. The pattern matching method is generally used in the field of image processing. For example, assuming that I(x, y) represents a read fingerprint image of a person to be identified, and T(x, y) represents a registered fingerprint image previously registered, an evaluation value v(x, y) is obtained by the following expression.
v(x, y)=(1/A)ΣΣI(i, j)T(i,-x, j-y) (1)
where A is the overlapping area between I(i, j) and T(i-x, j-y). Coordinates (x, y) where v is the maximum indicate a position where the read fingerprint image and the registered fingerprint image match each other to the maximum extent, and the value at that time represents the matching degree. - If the read fingerprint image and the registered fingerprint image are binary images of white and black, I(x, y) and T(x, y) take the value of 0 or 1. The evaluation value at this time may be obtained by the expression (1) given above, or by the following expression (2). As explained above, the expression used to perform a correlation operation is not limited thereto, but has various forms.
v(x, y)=(1/A)ΣΣnot(I(i, j) xor T(i-x, j-y)) (2)
where “xor” represents an exclusive OR, and “not” represents negative, and A is the overlapping area between I(i, j) and T(i-x, j-y). - However, the pattern matching method used in the conventional fingerprint identification device has one significant problem. This is the overlapping area between the read fingerprint image and the registered fingerprint image.
- In the expression (1) and the expression (2), a factor A corresponds to the area of the overlap. To calculate an accurate matching degree, the area needs to be divided by the factor A to normalize it. However, if the area of the overlap is small, the factor A as a denominator reduces, which causes the value of matching degree to be inaccurate. In order to obtain an accurate value, the area of the overlap is required to be about a half of the fingerprint image. Therefore, to obtain the larger area of the overlap, it is effective to use an image sensor having large area. Basically, by using an image sensor larger than the area of a finger, the overlap occupies most part of the image, and the problem does not occur.
- However, recently, requirements for installing the fingerprint identification device in portable terminals such as PDA, cellular phone, PHS, compact notebook-type personal computer, and the like are significantly increasing.
- This is because the functions of the portable terminal have become extremely advanced, and the information stored therein has increased, thereby increasing the risk of losing the information stored.
- However, in these portable terminals, it is difficult to install an image sensor whose size is larger than a finger (larger than 10 mm square) rather than restriction to installation space. Particularly, in cellular phones and PDAs, an image sensor having the area of about a fraction of a finger can be installed. In the image sensor having such small area, it is extremely difficult to exhibit sufficient performance, and therefore, it is impossible to perform fingerprint identification with high accuracy.
- A conventional art has been disclosed, for example, in Japanese Patent Application Laid-Open No. H10-187982.
- It is an object of the invention to at least solve the problems in the conventional technology.
- According to an aspect of the present invention, a fingerprint identification device includes a relative position calculating unit that calculates a relative position for each of registered fingerprint images, each of which is registered for each of a plurality of parts of one finger of a person; a image acquiring unit that acquires an image of a part of a finger of a person to be identified, as a read fingerprint image; a specifying unit that specifies a registered fingerprint image from among the registered fingerprint images, based on the relative position; a matching degree calculating unit that calculates a matching degree between the read fingerprint image and the registered fingerprint image specified; and an authenticating unit that authenticates a fingerprint if the matching degree is greater than a predetermined value.
- According to another aspect of the present invention, a method of fingerprint identification includes registering a fingerprint image, as registered fingerprint images, for each of a plurality of parts of one finger of a person; calculating a relative position for each of the registered fingerprint images; acquiring an image of a part of a finger of a person to be identified, as a read fingerprint image; specifying a registered fingerprint image from among the registered fingerprint images, based on the relative position; calculating a matching degree between the registered fingerprint image specified and the read fingerprint image; executing the specifying and the calculating until the matching degree is greater than a predetermined value.
- According to still another aspect of the present invention, a computer-readable recording medium stores therein a computer program that implements the above method on a computer.
- The other objects, features, and advantages of the present invention are specifically set forth in or will become apparent from the following detailed description of the invention when read in conjunction with the accompanying drawings.
-
FIG. 1 is a perspective view of an exterior of a portable terminal, to which a fingerprint identification device according to the present invention is applied; -
FIG. 2 is a block diagram of an electrical configuration of the portable terminal shown inFIG. 1 ; -
FIG. 3 is a diagram of a registered fingerprint image information group that is registered in a RAM shown inFIG. 2 ; -
FIG. 4 is a diagram of a relative positional relation between various fingerprint images; -
FIG. 5 is a diagram for explaining a fingerprint comparison process; -
FIG. 6 is a diagram of one search area; -
FIG. 7 is a diagram of a whole search area; -
FIG. 8 is a diagram of the whole search area; -
FIG. 9 is a diagram for explaining a fingerprint re-registration process; -
FIG. 10 is a flowchart for explaining an operation of the embodiment; -
FIG. 11 is a flowchart for explaining a fingerprint registration process shown inFIG. 10 ; -
FIG. 12 is a flowchart for explaining a fingerprint comparison process shown inFIG. 10 ; and -
FIG. 13 is a flowchart for explaining a fingerprint re-registration process shown inFIG. 10 . - Exemplary embodiments of the present invention are explained in detail below with reference to the accompanying drawings.
FIG. 1 is a perspective view of an exterior of aportable terminal 100 to which a fingerprint identification device according to one embodiment of the present invention is applied.FIG. 2 is a block diagram of an electrical configuration of theportable terminal 100 shown inFIG. 1 . - In these figures, the
portable terminal 100 includes an information processing function and a communication function, and further includes a fingerprint registration function, a fingerprint comparison function, and a fingerprint re-registration function, etc. Ahousing 110 shown inFIG. 1 includes adisplay unit 150 and animage sensor 170. Thedisplay unit 150 is a liquid crystal display for displaying various types of information. Atouch panel 160 adheres to thedisplay unit 150. Astylus 190 is used to touch thetouch panel 160, and input a character and so on, like a keyboard. - The
image sensor 170 reads a fingerprint image, and has an area that is smaller than the area of a fingerprint portion of a finger, for example, 3 mm square to 10 mm square. Therefore, only a part of a fingerprint can be read in one reading by theimage sensor 170. - As shown in
FIG. 2 , a CPU (central processing unit) 120 executes a computer program stored in a ROM (read-only memory) 130 to realize the information processing function, the communication function, the fingerprint registration function, the fingerprint comparison function, and the fingerprint re-registration function, etc. - The
ROM 130 stores the computer program and various types of data. A RAM (random access memory) 140 is a rewritable memory. In addition to the various types of data, a registered fingerprintimage information group 200 as shown inFIG. 3 is registered in theRAM 140. - As shown in
FIG. 4 , the registered fingerprintimage information group 200 corresponds to six registered fingerprint images 230 1 to 230 6 (images of various parts of the fingerprint) that are read by theimage sensor 170 six times and registered. The registered fingerprintimage information group 200 includes registeredfingerprint image information 210 1 to 210 6, andsupplementary information 220 1 to 220 6. - The registered
fingerprint image information 210 1 to 210 6 are fingerprint image information corresponding to the registeredfingerprint images 2301 to 2306 of six parts of afingerprint 310 of afinger 300 as shown inFIG. 4 , and are read by theimage sensor 170. These registeredfingerprint images 2301 to 2306 cover almost entire of thefingerprint 310 of thefinger 300, and overlap one another. - The
supplementary information 220 1 to 220 6 are correlated to the registeredfingerprint image information 210 1 to 210 6, respectively, and each of them includes information such as a registered fingerprint image number, a relative-position X coordinate, a relative-position Y coordinate, and a registered date & time. - The registered fingerprint image number is a unique number assigned to the registered fingerprint image information (registered fingerprint image). The relative-position X coordinate and the relative-position Y coordinate are X coordinate and Y coordinate assuming that in the registered fingerprint images 230 1 to 230 6, for example, a left upper point P1(0, 0) of the registered fingerprint image 230 1, which is read first, is an origin. The X coordinate and the Y coordinate represent a relative position between the left upper point P1 and a left upper point of another registered fingerprint image. The registered date & time indicates a date & time on which the registered fingerprint image information is registered in the
RAM 140. - Referring back to
FIG. 2 , acommunication interface 180 is an interface connected to a network (not shown) based on a predetermined communication protocol, and is used to perform communication with another portable terminal and the like. - Operating principles of one embodiment are explained below with reference to
FIG. 5 toFIG. 9 . - First, upon identification of a fingerprint, the image sensor 170 (see
FIG. 1 andFIG. 2 ) reads a part of the fingerprint of a person to be identified as aread fingerprint image 400, as shown inFIG. 5 . - In this case, the read
fingerprint image 400 is assumed to correspond to apart 320 of thefinger 300. A registered fingerprint image 230 5, having the broadest area of an overlap with thepart 320, is selected from the registered fingerprint images 230 1 to 230 6. Then, the value of matching degree is calculated, between the registered fingerprint image 230 5 and the readfingerprint image 400. - Thereafter, the
part 320 is shifted little by little by a predetermined distance, so as to cover the whole area throughout thefingerprint 310 of the finger 300 (area obtained by slightly increasing an area of the registered fingerprint images 230 1 to 230 6), and the values of matching degree are calculated each time. Of all these values, the highest value of the matching degree being is regarded as the final value of matching degree. - Such a search method allows the amount of calculation to be largely reduced as compared with a case where values of matching degree between the registered fingerprint images and the read fingerprint images are calculated in a “round robin” manner.
- That is, a range of a margin slightly increased with respect to the registered fingerprint image is assumed as a range of which a half of the area can be shared by the read fingerprint image and the registered fingerprint image. If so, as shown in
FIG. 6 , a search area of the maximum value of matching degree for one registered fingerprint image includes the registered fingerprint image 230 1 and a diagonally shaded area 240 1. The whole search area (the registered fingerprint images 230 1 to 230 6 and diagonally shaded areas 240 1 to 240 6) is shown inFIG. 7 . - Assume here that the registered fingerprint image 230 1 of
FIG. 6 consists of 96 pixels square. The diagonally shaded area 240 1 is assumed to have 23904 pixels. Therefore, the search area (the registered fingerprint image 230 1 and the diagonally shaded area 240 1) consists of 33120 pixels. - When the six registered fingerprint images 230 1 to 230 6 as shown in
FIG. 7 are used, the number of pixels of the whole search area (total of search areas) is 198720 (33120×6) pixels. - On the other hand, the whole search area in the search method as explained with reference to
FIG. 5 indicates the registered fingerprint images 230 1 to 230 6 in the overlapping state and a diagonally shadedarea 250 around, as shown inFIG. 8 . Therefore, this whole search area is less than the whole search area ofFIG. 7 . - More specifically, the diagonally shaded
area 250 shown inFIG. 8 has 42583 pixels. The registered fingerprint images 230 1 to 230 6 in the overlapping state have 34655 pixels. In other words, the whole search area as shown inFIG. 8 has 77238 (42583+34655) pixels, which is a half or less than the whole search area (198720 pixels) ofFIG. 7 . - Therefore, the search method of the present invention allows reduction in the amount of calculation, because the area to be searched can be largely reduced.
- In one embodiment, if the read fingerprint image is verified with a high matching degree, a fingerprint re-registration process is executed, in which an unnecessary registered fingerprint image is deleted and the read fingerprint image is re-registered as a new registered fingerprint image.
- For example, as shown in
FIG. 9 , if a read fingerprint image 230 NEW read by the image sensor 170 (seeFIG. 1 andFIG. 2 ) matches to a large extent another registered fingerprint image at the position shown in the figure, and if the read fingerprint image 230 NEW is to be registered, then the range to be covered largely increases as compared with the registered fingerprint image 230 2. - Therefore, addition of the read fingerprint image 230 NEW as a registered fingerprint image is useful for improvement of identification performance.
- However, there are some problems. One problem is that a fingerprint image of another person may be erroneously registered, and another problem is that the number of registered fingerprint images that can be stored in the
RAM 140 is generally limited. The problem of registering another person's fingerprint image may be avoided by using a method of checking the fingerprint image twice, or a method of registering the fingerprint image when the value of matching degree is sufficiently high. - For example, when the value of matching degree of the fingerprint is calculated a threshold value of 1/10,000 or a threshold value of 1/1 million may be set as a false acceptance rate.
- If the fingerprint identification device is operated based on the false acceptance rate as 1/10,000, a match is determined in both of the cases. Therefore, only if the false acceptance rate is the threshold value of 1/1 million in the latter case, the read fingerprint image 230 NEW is registered.
- In this case, chances of erroneous registration of others' fingerprint image can be eliminated almost completely. The problem that the fingerprint cannot be increased unlimitedly can be resolved by deleting an unnecessary registered fingerprint image when a registered fingerprint image is registered.
- For example, the whole area of the registered fingerprint image 230 3 of
FIG. 9 overlaps the other registered fingerprint images. In other words, even if the registered fingerprint image 230 3 is not present, the other registered fingerprint images can substitute it. Therefore, to re-register a new read fingerprint image 230 NEW, any registered fingerprint image (registeredfingerprint image 2303 in this case) that can be substituted with other registered fingerprint images is searched for, and is deleted. This allows increase in a range that covers the registered fingerprint images, without increase in the memory capacity of theRAM 140 in which the read fingerprint image 23ONEW is registered. - Furthermore, by re-registering a registered fingerprint image, it is also possible to prevent degradation in performance due to a change of a finger with time. For example, if a fingerprint image is registered when a user hurts his/her finger, the finger is getting better with the passage of time. Therefore, when the finger heals, identification may not be carried out properly. By sequentially re-registering registered fingerprint images, it is possible to perform excellent identification at any time according to the change of the finger with the passage of time.
- The operation of one embodiment is explained in detail below with reference to flowcharts in
FIG. 10 toFIG. 13 . At step SA1 ofFIG. 10 , the CPU 120 (seeFIG. 2 ) of theportable terminal 100 determines whether a user issues a fingerprint registration request for newly registering the registered fingerprint image information group 200 (seeFIG. 3 ) in theRAM 140, and sets the result of determination to “No” in this case. - At step SA2, the
CPU 120 determines whether there is a fingerprint identification request, and sets the result of determination to “No” in this case. At step SA3, theCPU 120 determines whether there is a fingerprint re-registration request, and sets the result of determination to “No” in this case. Thereafter, theCPU 120 repeats determinations at step SA1 to step SA3 until it is determined as Yes” at any of step SA1 to step SA3. - If there is the fingerprint registration request, the
CPU 120 sets the result of determination at step SA1 to “Yes”. At step SA4, theCPU 120 executes the fingerprint registration process. - More specifically, at step SB1 shown in
FIG. 11 , theCPU 120 causes thedisplay unit 150 to display “Put a finger on the sensor”, and prompts the person to be registered to put the finger on theimage sensor 170. With this prompt, the person to be registered puts the finger on theimage sensor 170. - At step SB2, the
image sensor 170 reads a part of the finger of the person to be registered as, for example, the registered fingerprint image 230 1 ofFIG. 4 . The registered fingerprint image 230 1 is a binary image of white and black. - At step SB3, the
CPU 120 causes thedisplay unit 150 to display “Fingerprint reading is complete. Lift the finger”, and prompts the person to be registered to lift the finger from theimage sensor 170. With this prompt, the person to be registered lifts the finger from theimage sensor 170. - At step SB4, the
CPU 120 determines whether it is the first time that the fingerprint image is read, and sets the result of determination to “Yes” in this case. - At step SB5, the
CPU 120 sets a relative position coordinate (XY coordinate system) of the registered fingerprint image 230 1 ofFIG. 4 to (0, 0), and generates thesupplementary information 220 1 in the format shown inFIG. 3 (in this case, registered fingerprint image number=1, relative-position X coordinate=0, relative-position Y coordinate=0, and registered date & time=present date & time). Then, theCPU 120 registers the registeredfingerprint image information 210, and thesupplementary information 220, corresponding to the registered fingerprint image 230 1 in theRAM 140. - Next, at step SB1, in the same manner as explained above, the
CPU 120 causes thedisplay unit 150 to display “Put a finger on the sensor”, and prompts the person to be registered to put the finger on theimage sensor 170. With this prompt, the person to be registered puts the finger on theimage sensor 170. In this case, because of human errors, a displacement arises between the position in which the finger is put for the first time and the position in which the finger is put for the second time. - At step SB2, the
image sensor 170 reads a part of the finger of the person to be registered as, for example, the registered fingerprint image 230 2 ofFIG. 4 . - At step SB3, the
CPU 120 causes thedisplay unit 150 to display “Fingerprint reading is complete. Lift the finger”, and prompts the person to be registered to lift the finger from theimage sensor 170. With this prompt, the person to be registered lifts the finger from theimage sensor 170. - At step SB4, the
CPU 120 determines whether it is the first time that the fingerprint image is read, and sets the result of determination to “No” in this case. - At step SB6, the
CPU 120 performs a correlation operation (the value of matching degree is calculated based on the matching pattern or the like) between the registered fingerprint image 230 2 read and each of the registered fingerprint images (in this case, only the registered fingerprint image 230 1) in the registered fingerprint image information group 200 (in this case, only the registeredfingerprint image information 210 1 and the supplementary information 220 1), and calculates each value of matching degree. - Next, the
CPU 120 determines the highest value of matching degree among the values of matching degree, a registered fingerprint image number of a registered fingerprint image corresponding to the highest value of matching degree, and an amount of relative positional displacement (x, y) between the two, and stores these pieces of information in theRAM 140. - At step SB7, the
CPU 120 determines whether the highest value of matching degree obtained at step SB6 exceeds a preset threshold value, and sets the result of determination to “Yes” in this case. If the result of determination at step SB7 is “No”, the process at step SB1 is executed. - At step SB8, the
CPU 120 calculates a relative position between the registered fingerprint image 230 1 (seeFIG. 4 ) having registered fingerprint image number as 1, and the registered fingerprint image 230 2 that corresponds to the highest value of matching degree. - Here, a relative-position X coordinate and a relative-position Y coordinate are calculated from the relative-position X coordinate and the relative-position Y coordinate that correspond to the registered fingerprint image that matches (in this case, registered fingerprint image 230 1), and also from the values of relative positional displacement (x, y). In this case, assuming that the values of the relative-position X coordinate and the relative-position Y coordinate corresponding to the registered fingerprint image 230 1 are set as Xs and Ys, and that the values of relative positional displacement (x, y) are set as Xo and Yo, relative-position X coordinate (Xnew) and Y coordinate (Ynew) are calculated using the following expression (3).
Xnew=Xs+Xo, Ynew=Ys+Yo (3) - At step SB9, the
CPU 120 generates supplementary information 220 2 (in this case, registered fingerprint image number=2, . . . ) corresponding to the registered fingerprint image 230 2 shown inFIG. 4 , and then registers the registeredfingerprint image information 210 2 and thesupplementary information 220 2 corresponding to the registered fingerprint image 230 2, in theRAM 140. - At step SB10, the
CPU 120 determines whether the number of registered fingerprint image information (supplementary information) registered in theRAM 140 is 6 (preset number), and sets the result of determination to “No” in this case. Thereafter, step SB1 to step SB4 and step SB6 to step SB10 are repeated, and the registeredfingerprint image information 210 3 to 210 6 (supplementary information 220 3 to 220 6) corresponding to the registered fingerprint images 230 3 to 230 6 ofFIG. 4 are sequentially registered in theRAM 140. With this registration, theCPU 120 sets the result of determination at step SB10 to “Yes”, and returns to the main routine ofFIG. 10 . Thus, fingerprint identification is achieved. - If the fingerprint identification request is received, the
CPU 120 sets the result of determination at step SA2 ofFIG. 10 to “Yes”. At step SA5, theCPU 120 executes the fingerprint comparison process. - More specifically, at step SC1 as shown in
FIG. 12 , theCPU 120 causes thedisplay unit 150 to display “Put a finger on the sensor”, and prompts the person to be identified to put the finger on theimage sensor 170. With this prompt, the person to be identified puts the finger on theimage sensor 170. - At step SC2, the
image sensor 170 reads a part of the finger of the person to be identified as, for example, the readfingerprint image 400 shown inFIG. 5 . The readfingerprint image 400 is a binary image of white and black. - At step SC3, the
CPU 120 decides a range (X, Y directions) to assume a position where the readfingerprint image 400 is present. More specifically, the X direction is a range from the smallest relative-position X coordinate to the largest relative-position X coordinate, among the six registered fingerprint images shown inFIG. 4 . On the other hand, the Y direction is a range from the smallest relative-position Y coordinate to the largest relative-position Y coordinate. - Actually, an area to be covered by the registered fingerprint images does not always cover the whole area of the finger, and therefore, it is appropriate that the area is extended to an area where the area may overlap a half of the finger.
- Assume that the smallest relative-position X coordinate is set as Xmin, the largest relative-position X coordinate as Xmax, the smallest relative-position Y coordinate as Ymin, the largest relative-position Y coordinate as Ymax, the size of a fingerprint image is set to have a width XL and a length YL. An assumption range is expressed by the following expression (4).
Range in X direction: Xmin−XL/2 to Xmax+XL/2 (4)
Range in Y direction: Ymin−YL/2 to Ymax+YL/2 - The
CPU 120 performs calculation on the whole assumption range based on assumption that the readfingerprint image 400 lies within that position. - At step SC4, when deciding a range assumed of the read
fingerprint image 400, theCPU 120 further decides one point in the range as a position assumed of the read fingerprint image 400 (coordinates of the point are set as XV, YV). - At step SC5, when assuming that any position of the range is a position in which the read
fingerprint image 400 is read, theCPU 120 determines whether there is a registered fingerprint image of which more than half area overlaps the readfingerprint image 400. - Herein, the overlapping area is expressed by the following expression (5) where Xn is a relative-position X coordinate and Yn is a relative-position Y coordinate.
|XV−Xn|<XL and |YV−Yn|<YL and (5)
(XL−|XV|Xn|)·(YL−|YV−Yn|)≧(XL·YL)/2 - If the result of determination at step SC5 is “No”, determination is performed at step SC10.
- On the other hand, if the result of determination at step SC5 is “Yes”, then, at step SC6, the
CPU 120 calculates the overlapping area using the following expression (6), and selects a registered fingerprint image in which the overlapping area S is the largest.
S=(XL−|XV−Xn|)·(YL−|YV−Yn|) (6) - At step SC7, the
CPU 120 calculates a value of matching degree between the registered fingerprint image selected at step SC6 and the readfingerprint image 400. More specifically, assuming the relative-position X coordinate and the relative-position Y coordinate of the registered fingerprint image selected are XS and YS, respectively, the value V of matching degree is expressed by the following expression (7). - Xsml is the larger of XS and XV, XIar is obtained by adding XL to the smaller of XS and XV, Ysml, is the larger of YS and YV, and YIar is obtained by adding YL to the smaller of YS and YV. Further, I(x, y) is a pixel value at a lower position by the coordinates x, y, from the left upper side of the read
fingerprint image 400, and T(x, y) is a pixel value at a lower position by the coordinates x, y, from the left upper side of the registered fingerprint image selected. - At step SC8, the
CPU 120 determines whether the value V of matching degree calculated at step SC7 exceeds the largest value among the values of matching degree in all the positions assumed so far, i.e., whether the value V exceeds the maximum value Vmax of matching degree. If the result of determination is “No”, determination is performed at step SC10. - On the other hand, if the result of determination at step SC8 is “Yes”, at step SC9, the
CPU 120 substitutes the value V of matching degree in the maximum value Vmax of matching degree, to update the maximum value Vmax of matching degree. - At step SC10, the
CPU 120 determines whether values of matching degree are calculated at all the positions in the range of the position assumed of the readfingerprint image 400, sets the result of determination to “No” in this case, and executes the process at the step SC4 and thereafter. Step SC4 to step SC10 are repeated until the result of determination at step SC10 is obtained as “Yes”. - If the result of determination at step SC10 is obtained as “Yes”, at step SC11, the
CPU 120 determines whether the maximum value Vmax of matching degree is equal to or more than the threshold value for comparison, and sets the result of determination to “Yes” in this case. At step SC12, theCPU 120 determines that a match is found, and authorizes that the person to be identified is identified as the person to be registered, and returns to the main routine ofFIG. 10 . - On the other hand, if the result of determination at step SC11 is “No”, at step SC13, the
CPU 120 determines that there is no match, determines that the person to be identified is not the person to be registered, and returns to the main routine ofFIG. 10 . - Upon receiving the fingerprint re-registration request, the
CPU 120 sets the result of determination at step SA3 ofFIG. 10 to “Yes”. At step SA6, theCPU 120 executes a fingerprint re-registration process. - More specifically, at step SD1 as shown in
FIG. 13 , theCPU 120 executes the fingerprint comparison process (seeFIG. 12 ) a first time. At step SD2, theCPU 120 determines whether a match is found as a result of comparison at step SD1. If the result of determination is “No”, theCPU 120 returns to the main routine ofFIG. 10 . - On the other hand, if the result of determination at step SD2 is “Yes”, at step SD3, the
CPU 120 executes the fingerprint comparison process (seeFIG. 12 ) a second time. At step SD4, theCPU 120 determines whether a match is found as a result of comparison at step SD3. If the result of determination is “No”, theCPU 120 returns to the main routine ofFIG. 10 . Here, by executing the fingerprint comparison process twice, it is possible to prevent unauthorized use of the device by a malicious third party, and to enhance reliability. - In this case, if the result of determination at step SD4 is “Yes”, at step SD5, the
CPU 120 selects one registered fingerprint image information (registered fingerprint image) from the registered fingerprint image information group 200 (seeFIG. 3 ). At step SD6, theCPU 120 secures a RAM area for checking, having the same size as the registered fingerprint image information in theRAM 140, and initializes all the values in the RAM area for checking to 0. - At step SD7, the
CPU 120 uses the values of the relative position to calculate an overlapping area between the registered fingerprint image selected at step SD5 and another registered fingerprint image, and stores the value of 1 in a portion corresponding to the position of the overlapping area in the RAM area for checking. - At step SD8, the
CPU 120 determines whether the value of 1 is stored in 90% or more of the RAM area for checking, and sets the result of determination to “No” in this case. At step SD9, theCPU 120 determines whether all the overlaps are checked, sets the result of determination to “No” in this case, and executes the process at step SD5 and thereafter. - If the result of determination at step SD9 is “Yes”, the
CPU 120 returns to the main routine ofFIG. 10 . - If the result of determination at step SD8 is “Yes”, at step SD10, the
CPU 120 deletes the relevant registered fingerprint image information and the supplementary information from the registered fingerprintimage information group 200. At step SD11, theCPU 120 causes theimage sensor 170 to read a new fingerprint image in the same manner as explained above. At step SD12, theCPU 120 re-registers in theRAM 140, new registered fingerprint image information and supplementary information that correspond to the fingerprint image, as the registered fingerprintimage information group 200. - According to the embodiment explained above, registered fingerprint images of the parts of one finger of a person to be registered are registered as the registered fingerprint
image information group 200. One registered fingerprint image is selected from a plurality of registered fingerprint images based on relative positions of the registered fingerprint images, to perform fingerprint identification based on a matching degree between the one registered fingerprint image and the read fingerprint image. Therefore, the present invention can be installed in a portable terminal having such a small-sized image sensor that reads only a part of the fingerprint of a finger, and hence, can achieve highly accurate fingerprint identification. Moreover, in the embodiment, the speed can be prevented from slowing. - Although one embodiment of the present invention has been explained in detail with reference to the drawings, examples of specific configurations are not limited to the above embodiment. Therefore, it is understood that changes and modifications in design may be made in the present invention without departing from the spirit and scope thereof.
- For example, in the above embodiment, a method of deciding which registered fingerprint image is to be deleted upon re-registration, may be changed as follows.
- That is, a function may be provided to store a date & time related to each registered fingerprint image. The function stores a date & time at fingerprint identification in a part where a particular date & time of a registered fingerprint image is stored. The particular date & time is the one when the highest value of matching degree about the registered fingerprint image is obtained, at the time of the fingerprint identification.
- If any new read fingerprint image to be registered comes up, the date & time related to all the registered fingerprint images are referred to. The registered fingerprint image that is dated about one month or more ago is deleted, and a new fingerprint image is re-registered. In many cases, the registered fingerprint image dated one month or more ago is not used, because there is a problem that a part of the fingerprint image may be distorted or missing.
- Registration of such a fingerprint image does not contribute to improvement of identification performance. Therefore, the fingerprint image is deleted, and a new fingerprint image is re-registered, to improve the identification performance.
- Furthermore, in the embodiment, if the value of matching degree adequate for re-registration of a fingerprint is obtained when fingerprint identification is performed, the date & time on which the fingerprint image is last re-registered is compared with the current date & time. If a difference between the two dates is about six months or more, all pieces of the registered fingerprint image information registered in the
RAM 140 are deleted, and the person to be identified is made to re-register fingerprint images until the number of registered fingerprint images reaches a specific number of images. Based on this, all the old fingerprint images are deleted, and new fingerprint images can be re-registered, thereby improving identification performance. In this case, the registered fingerprint image is updated according to a change of a finger with the passage of time, which allows fingerprint identification with high accuracy at any time. - As explained above, the present invention can be installed even in a portable terminal having a small-sized image sensor that can read only a part of the fingerprint of a finger, and can achieve highly accurate fingerprint identification.
- Although the invention has been described with respect to a specific embodiment for a complete and clear disclosure, the appended claims are not to be thus limited but are to be construed as embodying all modifications and alternative constructions that may occur to one skilled in the art that fairly fall within the basic teaching herein set forth.
Claims (14)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2003/005374 WO2004097741A1 (en) | 2003-04-25 | 2003-04-25 | Fingerprint matching device, fingerprint matching method, and fingerprint matching program |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2003/005374 Continuation WO2004097741A1 (en) | 2003-04-25 | 2003-04-25 | Fingerprint matching device, fingerprint matching method, and fingerprint matching program |
Publications (2)
Publication Number | Publication Date |
---|---|
US20050185828A1 true US20050185828A1 (en) | 2005-08-25 |
US7359534B2 US7359534B2 (en) | 2008-04-15 |
Family
ID=33398115
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/109,765 Expired - Lifetime US7359534B2 (en) | 2003-04-25 | 2005-04-20 | Device and method for fingerprint identification, and computer product |
Country Status (5)
Country | Link |
---|---|
US (1) | US7359534B2 (en) |
EP (1) | EP1619622B1 (en) |
JP (1) | JP4068622B2 (en) |
DE (1) | DE60330276D1 (en) |
WO (1) | WO2004097741A1 (en) |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050110964A1 (en) * | 2002-05-28 | 2005-05-26 | Matthew Bell | Interactive video window display system |
US20070177767A1 (en) * | 2006-02-02 | 2007-08-02 | Naoto Miura | Biometric information processing device and biometric information processing program |
US20080144894A1 (en) * | 2006-08-11 | 2008-06-19 | Vladimir Nickolaevich Bichigov | Method for filtering a fingerprint image continuation-in-part |
US20090141951A1 (en) * | 2007-11-30 | 2009-06-04 | Sharp Kabushiki Kaisha | Processing apparatus with touch panel |
US7834846B1 (en) | 2001-06-05 | 2010-11-16 | Matthew Bell | Interactive video display system |
US8035612B2 (en) | 2002-05-28 | 2011-10-11 | Intellectual Ventures Holding 67 Llc | Self-contained interactive video display system |
US8081822B1 (en) * | 2005-05-31 | 2011-12-20 | Intellectual Ventures Holding 67 Llc | System and method for sensing a feature of an object in an interactive video display |
US8098277B1 (en) | 2005-12-02 | 2012-01-17 | Intellectual Ventures Holding 67 Llc | Systems and methods for communication between a reactive video system and a mobile communication device |
US8159682B2 (en) | 2007-11-12 | 2012-04-17 | Intellectual Ventures Holding 67 Llc | Lens system |
US8199108B2 (en) | 2002-12-13 | 2012-06-12 | Intellectual Ventures Holding 67 Llc | Interactive directed light/sound system |
US8230367B2 (en) | 2007-09-14 | 2012-07-24 | Intellectual Ventures Holding 67 Llc | Gesture-based user interactions with status indicators for acceptable inputs in volumetric zones |
US8259163B2 (en) | 2008-03-07 | 2012-09-04 | Intellectual Ventures Holding 67 Llc | Display with built in 3D sensing |
US8300042B2 (en) | 2001-06-05 | 2012-10-30 | Microsoft Corporation | Interactive video display system using strobed light |
US20120304267A1 (en) * | 2011-05-27 | 2012-11-29 | Fujitsu Limited | Biometric authentication device and biometric authentication method |
US20120326841A1 (en) * | 2010-03-08 | 2012-12-27 | Fujitsu Limited | Biometric authentication apparatus and method |
US8487866B2 (en) | 2003-10-24 | 2013-07-16 | Intellectual Ventures Holding 67 Llc | Method and system for managing an interactive video display system |
US20130259330A1 (en) * | 2012-03-27 | 2013-10-03 | Validity Sensors, Inc. | Method of and system for enrolling and matching biometric data |
US8595218B2 (en) | 2008-06-12 | 2013-11-26 | Intellectual Ventures Holding 67 Llc | Interactive display management systems and methods |
US20150086090A1 (en) * | 2013-09-24 | 2015-03-26 | Samsung Electronics Co., Ltd. | Electronic device including fingerprint identification sensor, methods for performing user authentication and registering user's fingerprint in electronic device including fingerprint identification sensor, and recording medium recording program for executing the methods |
US9128519B1 (en) | 2005-04-15 | 2015-09-08 | Intellectual Ventures Holding 67 Llc | Method and system for state-based control of objects |
WO2015174632A1 (en) * | 2014-05-13 | 2015-11-19 | Samsung Electronics Co., Ltd. | Method of controlling mobile terminal using fingerprint recognition and mobile terminal using the same |
WO2016072921A1 (en) * | 2014-11-07 | 2016-05-12 | Fingerprint Cards Ab | Fingerprint authentication using stitch and cut |
US9400914B2 (en) * | 2014-10-24 | 2016-07-26 | Egis Technology Inc. | Method and electronic device for generating fingerprint enrollment data |
EP3086262A1 (en) * | 2015-04-23 | 2016-10-26 | Samsung Electronics Co., Ltd. | Fingerprint verification method and apparatus |
US9508122B2 (en) | 2014-11-07 | 2016-11-29 | Fingerprint Cards Ab | Creating templates for fingerprint authentication |
CN106326833A (en) * | 2015-07-01 | 2017-01-11 | 艾戴克斯公司 | System and method of biometric enrollment and verification |
US20170032169A1 (en) * | 2014-09-06 | 2017-02-02 | Shenzhen Huiding Technology Co., Ltd. | Swipe motion registration on a fingerprint sensor |
US10102413B2 (en) | 2015-05-08 | 2018-10-16 | Fujitsu Limited | Biometric imaging device and biometric imaging method |
US10229258B2 (en) * | 2013-03-27 | 2019-03-12 | Samsung Electronics Co., Ltd. | Method and device for providing security content |
US10282614B2 (en) * | 2016-02-18 | 2019-05-07 | Microsoft Technology Licensing, Llc | Real-time detection of object scanability |
CN109964231A (en) * | 2016-09-14 | 2019-07-02 | 爱德克斯公司 | Dynamic registration seed |
CN114299639A (en) * | 2021-11-22 | 2022-04-08 | 浙江零跑科技股份有限公司 | Automobile trunk opening method and system based on finger vein recognition |
CN114407737A (en) * | 2021-12-15 | 2022-04-29 | 浙江零跑科技股份有限公司 | Seat memory adjusting method based on finger vein recognition |
US11373439B1 (en) * | 2013-03-14 | 2022-06-28 | Telos Corporation | Touchless fingerprint matching systems and methods |
EP3835981A4 (en) * | 2018-08-07 | 2022-07-20 | Kabushiki Kaisha Tokai Rika Denki Seisakusho | Biometric information authentication device |
US11468722B2 (en) * | 2018-10-02 | 2022-10-11 | Nec Corporation | Information processing apparatus, information processing system, and information processing method |
US11711562B2 (en) | 2019-09-06 | 2023-07-25 | Tencent America LLC | In-manifest update event |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007052720A (en) * | 2005-08-19 | 2007-03-01 | Fujitsu Ltd | Information access method by biometrics authentication and information processing system by biometrics authentication |
CN101276411B (en) * | 2008-05-12 | 2010-06-02 | 北京理工大学 | Fingerprint identification method |
JP6089610B2 (en) * | 2012-11-13 | 2017-03-08 | 富士通株式会社 | Biometric authentication apparatus, biometric authentication method, and biometric authentication computer program |
USD745888S1 (en) * | 2013-09-03 | 2015-12-22 | Samsung Electronics Co., Ltd. | Display screen or portion thereof with icon |
USD741889S1 (en) * | 2013-09-10 | 2015-10-27 | Apple Inc. | Display screen or portion thereof with animated graphical user interface |
US20150178727A1 (en) * | 2013-12-23 | 2015-06-25 | Tencent Technology (Shenzhen) Company Limited | Systems and Methods for Identity Verification for Terminal-Based Payments |
KR102236279B1 (en) * | 2014-06-17 | 2021-04-02 | 엘지전자 주식회사 | Mobile terminal and method for controlling the same |
USD755839S1 (en) * | 2014-09-09 | 2016-05-10 | Apple Inc. | Display screen or portion thereof with graphical user interface |
CN105205439B (en) * | 2015-02-13 | 2017-05-03 | 比亚迪股份有限公司 | Method for calculating area of fingerprint overlapping region and electronic device |
TWI617937B (en) * | 2015-02-24 | 2018-03-11 | Fingerprint encoding method, fingerprint authentication method and system | |
KR102205495B1 (en) * | 2015-04-15 | 2021-01-21 | 삼성전자주식회사 | Method and apparatus for recognizing finger print |
US10032062B2 (en) * | 2015-04-15 | 2018-07-24 | Samsung Electronics Co., Ltd. | Method and apparatus for recognizing fingerprint |
KR102387569B1 (en) * | 2015-04-23 | 2022-04-19 | 삼성전자주식회사 | Method and apparatus for verifying fingerprint |
KR20160136013A (en) * | 2015-05-19 | 2016-11-29 | 엘지전자 주식회사 | Mobile terminal and method for controlling the same |
KR102415504B1 (en) * | 2015-06-30 | 2022-07-04 | 삼성전자주식회사 | Updating method and apparatus of registration database for user authentication |
USD786932S1 (en) * | 2015-08-12 | 2017-05-16 | Samsung Electronics Co., Ltd. | Display screen or portion thereof with animated graphical user interface |
KR101990285B1 (en) * | 2015-11-24 | 2019-06-18 | 주식회사 슈프리마 | Method and apparatus for fingerprint recognition |
USD804508S1 (en) | 2016-10-26 | 2017-12-05 | Apple Inc. | Display screen or portion thereof with graphical user interface |
USD1007521S1 (en) | 2021-06-04 | 2023-12-12 | Apple Inc. | Display screen or portion thereof with graphical user interface |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5917928A (en) * | 1997-07-14 | 1999-06-29 | Bes Systems, Inc. | System and method for automatically verifying identity of a subject |
US5982913A (en) * | 1997-03-25 | 1999-11-09 | The United States Of America As Represented By The National Security Agency | Method of verification using a subset of claimant's fingerprint |
US6393139B1 (en) * | 1999-02-23 | 2002-05-21 | Xirlink, Inc. | Sequence-encoded multiple biometric template security system |
US6434259B1 (en) * | 1998-04-24 | 2002-08-13 | Activcard Ireland Limited | Method of providing secure user access |
US20030126448A1 (en) * | 2001-07-12 | 2003-07-03 | Russo Anthony P. | Method and system for biometric image assembly from multiple partial biometric frame scans |
US20050147282A1 (en) * | 2003-04-15 | 2005-07-07 | Fujitsu Limited | Image matching apparatus, image matching method, and image matching program |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10143663A (en) * | 1996-11-13 | 1998-05-29 | Hamamatsu Photonics Kk | Fingerprint information processor |
JPH10187982A (en) * | 1996-12-26 | 1998-07-21 | Sony Corp | Image collating device |
US7236617B1 (en) * | 2000-04-13 | 2007-06-26 | Nanyang Technological University | Method and device for determining a total minutiae template from a plurality of partial minutiae templates |
JP4164732B2 (en) * | 2001-03-07 | 2008-10-15 | ソニー株式会社 | Fingerprint verification system, fingerprint verification device, fingerprint verification method, and biometric verification device |
US7720262B2 (en) * | 2002-02-18 | 2010-05-18 | Precise Biometrics Ab | Method and device for recording fingerprint data |
-
2003
- 2003-04-25 EP EP03719215A patent/EP1619622B1/en not_active Expired - Lifetime
- 2003-04-25 JP JP2004571289A patent/JP4068622B2/en not_active Expired - Fee Related
- 2003-04-25 DE DE60330276T patent/DE60330276D1/en not_active Expired - Lifetime
- 2003-04-25 WO PCT/JP2003/005374 patent/WO2004097741A1/en active Application Filing
-
2005
- 2005-04-20 US US11/109,765 patent/US7359534B2/en not_active Expired - Lifetime
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5982913A (en) * | 1997-03-25 | 1999-11-09 | The United States Of America As Represented By The National Security Agency | Method of verification using a subset of claimant's fingerprint |
US5917928A (en) * | 1997-07-14 | 1999-06-29 | Bes Systems, Inc. | System and method for automatically verifying identity of a subject |
US6434259B1 (en) * | 1998-04-24 | 2002-08-13 | Activcard Ireland Limited | Method of providing secure user access |
US6393139B1 (en) * | 1999-02-23 | 2002-05-21 | Xirlink, Inc. | Sequence-encoded multiple biometric template security system |
US20030126448A1 (en) * | 2001-07-12 | 2003-07-03 | Russo Anthony P. | Method and system for biometric image assembly from multiple partial biometric frame scans |
US20050147282A1 (en) * | 2003-04-15 | 2005-07-07 | Fujitsu Limited | Image matching apparatus, image matching method, and image matching program |
Cited By (66)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8300042B2 (en) | 2001-06-05 | 2012-10-30 | Microsoft Corporation | Interactive video display system using strobed light |
US7834846B1 (en) | 2001-06-05 | 2010-11-16 | Matthew Bell | Interactive video display system |
US8035624B2 (en) | 2002-05-28 | 2011-10-11 | Intellectual Ventures Holding 67 Llc | Computer vision based touch screen |
US20050110964A1 (en) * | 2002-05-28 | 2005-05-26 | Matthew Bell | Interactive video window display system |
US8035614B2 (en) | 2002-05-28 | 2011-10-11 | Intellectual Ventures Holding 67 Llc | Interactive video window |
US7710391B2 (en) | 2002-05-28 | 2010-05-04 | Matthew Bell | Processing an image utilizing a spatially varying pattern |
US8035612B2 (en) | 2002-05-28 | 2011-10-11 | Intellectual Ventures Holding 67 Llc | Self-contained interactive video display system |
US8199108B2 (en) | 2002-12-13 | 2012-06-12 | Intellectual Ventures Holding 67 Llc | Interactive directed light/sound system |
US8487866B2 (en) | 2003-10-24 | 2013-07-16 | Intellectual Ventures Holding 67 Llc | Method and system for managing an interactive video display system |
US9128519B1 (en) | 2005-04-15 | 2015-09-08 | Intellectual Ventures Holding 67 Llc | Method and system for state-based control of objects |
US8081822B1 (en) * | 2005-05-31 | 2011-12-20 | Intellectual Ventures Holding 67 Llc | System and method for sensing a feature of an object in an interactive video display |
US8098277B1 (en) | 2005-12-02 | 2012-01-17 | Intellectual Ventures Holding 67 Llc | Systems and methods for communication between a reactive video system and a mobile communication device |
US9171233B2 (en) * | 2006-02-02 | 2015-10-27 | Hitachi, Ltd. | Biometric information processing device and biometric information processing program |
US20070177767A1 (en) * | 2006-02-02 | 2007-08-02 | Naoto Miura | Biometric information processing device and biometric information processing program |
US20080144894A1 (en) * | 2006-08-11 | 2008-06-19 | Vladimir Nickolaevich Bichigov | Method for filtering a fingerprint image continuation-in-part |
US8526687B2 (en) | 2006-11-08 | 2013-09-03 | Vladimir Nickolaevich Bichigov | Method for filtering a fingerprint image continuation-in-part |
US9058058B2 (en) | 2007-09-14 | 2015-06-16 | Intellectual Ventures Holding 67 Llc | Processing of gesture-based user interactions activation levels |
US9811166B2 (en) | 2007-09-14 | 2017-11-07 | Intellectual Ventures Holding 81 Llc | Processing of gesture-based user interactions using volumetric zones |
US10564731B2 (en) | 2007-09-14 | 2020-02-18 | Facebook, Inc. | Processing of gesture-based user interactions using volumetric zones |
US10990189B2 (en) | 2007-09-14 | 2021-04-27 | Facebook, Inc. | Processing of gesture-based user interaction using volumetric zones |
US8230367B2 (en) | 2007-09-14 | 2012-07-24 | Intellectual Ventures Holding 67 Llc | Gesture-based user interactions with status indicators for acceptable inputs in volumetric zones |
US9229107B2 (en) | 2007-11-12 | 2016-01-05 | Intellectual Ventures Holding 81 Llc | Lens system |
US8810803B2 (en) | 2007-11-12 | 2014-08-19 | Intellectual Ventures Holding 67 Llc | Lens system |
US8159682B2 (en) | 2007-11-12 | 2012-04-17 | Intellectual Ventures Holding 67 Llc | Lens system |
US8332933B2 (en) * | 2007-11-30 | 2012-12-11 | Sharp Kabushiki Kaisha | Processing apparatus with touch panel |
US20090141951A1 (en) * | 2007-11-30 | 2009-06-04 | Sharp Kabushiki Kaisha | Processing apparatus with touch panel |
US9247236B2 (en) | 2008-03-07 | 2016-01-26 | Intellectual Ventures Holdings 81 Llc | Display with built in 3D sensing capability and gesture control of TV |
US8259163B2 (en) | 2008-03-07 | 2012-09-04 | Intellectual Ventures Holding 67 Llc | Display with built in 3D sensing |
US10831278B2 (en) | 2008-03-07 | 2020-11-10 | Facebook, Inc. | Display with built in 3D sensing capability and gesture control of tv |
US8595218B2 (en) | 2008-06-12 | 2013-11-26 | Intellectual Ventures Holding 67 Llc | Interactive display management systems and methods |
US9013271B2 (en) * | 2010-03-08 | 2015-04-21 | Fujitsu Limited | Biometric authentication apparatus and method |
US20120326841A1 (en) * | 2010-03-08 | 2012-12-27 | Fujitsu Limited | Biometric authentication apparatus and method |
US8661516B2 (en) * | 2011-05-27 | 2014-02-25 | Fujitsu Limited | Biometric authentication device and biometric authentication method |
US20120304267A1 (en) * | 2011-05-27 | 2012-11-29 | Fujitsu Limited | Biometric authentication device and biometric authentication method |
US20160162725A1 (en) * | 2012-03-27 | 2016-06-09 | Synaptics Incorporated | Method of and system for enrolling and matching biometric data |
US9268991B2 (en) * | 2012-03-27 | 2016-02-23 | Synaptics Incorporated | Method of and system for enrolling and matching biometric data |
US20130259330A1 (en) * | 2012-03-27 | 2013-10-03 | Validity Sensors, Inc. | Method of and system for enrolling and matching biometric data |
US11373439B1 (en) * | 2013-03-14 | 2022-06-28 | Telos Corporation | Touchless fingerprint matching systems and methods |
US10229258B2 (en) * | 2013-03-27 | 2019-03-12 | Samsung Electronics Co., Ltd. | Method and device for providing security content |
US10824707B2 (en) * | 2013-03-27 | 2020-11-03 | Samsung Electronics Co., Ltd. | Method and device for providing security content |
US20150086090A1 (en) * | 2013-09-24 | 2015-03-26 | Samsung Electronics Co., Ltd. | Electronic device including fingerprint identification sensor, methods for performing user authentication and registering user's fingerprint in electronic device including fingerprint identification sensor, and recording medium recording program for executing the methods |
US9235746B2 (en) * | 2013-09-24 | 2016-01-12 | Samsung Electronics Co., Ltd. | Electronic device including fingerprint identification sensor, methods for performing user authentication and registering user's fingerprint in electronic device including fingerprint identification sensor, and recording medium recording program for executing the methods |
WO2015174632A1 (en) * | 2014-05-13 | 2015-11-19 | Samsung Electronics Co., Ltd. | Method of controlling mobile terminal using fingerprint recognition and mobile terminal using the same |
US20170032169A1 (en) * | 2014-09-06 | 2017-02-02 | Shenzhen Huiding Technology Co., Ltd. | Swipe motion registration on a fingerprint sensor |
US9400914B2 (en) * | 2014-10-24 | 2016-07-26 | Egis Technology Inc. | Method and electronic device for generating fingerprint enrollment data |
EP3215979A4 (en) * | 2014-11-07 | 2018-06-20 | Fingerprint Cards AB | Fingerprint authentication using stitch and cut |
WO2016072921A1 (en) * | 2014-11-07 | 2016-05-12 | Fingerprint Cards Ab | Fingerprint authentication using stitch and cut |
US9613428B2 (en) | 2014-11-07 | 2017-04-04 | Fingerprint Cards Ab | Fingerprint authentication using stitch and cut |
US9508122B2 (en) | 2014-11-07 | 2016-11-29 | Fingerprint Cards Ab | Creating templates for fingerprint authentication |
CN105981046A (en) * | 2014-11-07 | 2016-09-28 | 指纹卡有限公司 | Fingerprint authentication using stitch and cut |
US11341767B2 (en) | 2015-04-23 | 2022-05-24 | Samsung Electronics Co., Ltd. | Fingerprint verification method and apparatus |
US11715325B2 (en) | 2015-04-23 | 2023-08-01 | Samsung Electronics Co., Ltd. | Fingerprint verification method and apparatus |
US10521642B2 (en) | 2015-04-23 | 2019-12-31 | Samsung Electronics Co., Ltd. | Fingerprint verification method and apparatus |
EP3086262A1 (en) * | 2015-04-23 | 2016-10-26 | Samsung Electronics Co., Ltd. | Fingerprint verification method and apparatus |
US10102413B2 (en) | 2015-05-08 | 2018-10-16 | Fujitsu Limited | Biometric imaging device and biometric imaging method |
CN106326833A (en) * | 2015-07-01 | 2017-01-11 | 艾戴克斯公司 | System and method of biometric enrollment and verification |
US10282614B2 (en) * | 2016-02-18 | 2019-05-07 | Microsoft Technology Licensing, Llc | Real-time detection of object scanability |
CN109964231A (en) * | 2016-09-14 | 2019-07-02 | 爱德克斯公司 | Dynamic registration seed |
US10395129B2 (en) * | 2016-09-14 | 2019-08-27 | Idex Asa | Dynamic registration seed |
EP3835981A4 (en) * | 2018-08-07 | 2022-07-20 | Kabushiki Kaisha Tokai Rika Denki Seisakusho | Biometric information authentication device |
US11948403B2 (en) | 2018-08-07 | 2024-04-02 | Kabushiki Kaisha Tokai Rika Denki Seisakusho | Biometric information authentication device |
US11468722B2 (en) * | 2018-10-02 | 2022-10-11 | Nec Corporation | Information processing apparatus, information processing system, and information processing method |
US12094275B2 (en) | 2018-10-02 | 2024-09-17 | Nec Corporation | Information processing apparatus, information processing system, and information processing method |
US11711562B2 (en) | 2019-09-06 | 2023-07-25 | Tencent America LLC | In-manifest update event |
CN114299639A (en) * | 2021-11-22 | 2022-04-08 | 浙江零跑科技股份有限公司 | Automobile trunk opening method and system based on finger vein recognition |
CN114407737A (en) * | 2021-12-15 | 2022-04-29 | 浙江零跑科技股份有限公司 | Seat memory adjusting method based on finger vein recognition |
Also Published As
Publication number | Publication date |
---|---|
EP1619622A1 (en) | 2006-01-25 |
JP4068622B2 (en) | 2008-03-26 |
EP1619622A4 (en) | 2007-04-18 |
JPWO2004097741A1 (en) | 2006-07-13 |
US7359534B2 (en) | 2008-04-15 |
DE60330276D1 (en) | 2010-01-07 |
WO2004097741A1 (en) | 2004-11-11 |
EP1619622B1 (en) | 2009-11-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7359534B2 (en) | Device and method for fingerprint identification, and computer product | |
US6233348B1 (en) | Fingerprint registering apparatus, fingerprint identifying apparatus, and fingerprint identifying method | |
KR100801515B1 (en) | Biometric information input device, biometric authentication device, biometric information processing method, and computer-readable recording medium recording biometric information processing program | |
US7079671B2 (en) | Authentication method, and program and apparatus therefor | |
US20080013805A1 (en) | Finger sensing device using indexing and associated methods | |
US6757410B1 (en) | Fingerprint verification system and fingerprint verifying method | |
EP2677495A1 (en) | Biometric authentication device, biometric authentication method, and computer program for biometric authentication | |
US20050174325A1 (en) | Electronic device with finger sensor for character entry and associated methods | |
EP0918300A2 (en) | Fingerprint feature correlator | |
US20010019622A1 (en) | Biometric data acceptance method | |
EP0650137A2 (en) | An apparatus for fingerprint verification | |
US20050105782A1 (en) | Biometric information obtaining apparatus | |
EP0646886A2 (en) | An apparatus for automatic fingerprint classification | |
US20070263912A1 (en) | Method Of Identifying An Individual From Image Fragments | |
JP2010526385A (en) | Sequential image alignment | |
EP1423821A1 (en) | Method and apparatus for checking a person's identity, where a system of coordinates, constant to the fingerprint, is the reference | |
WO2013145280A1 (en) | Biometric authentication device, biometric authentication method, and biometric authentication computer program | |
US7035444B2 (en) | System for fingerprint authentication based of ridge shape | |
JP2001351103A (en) | Device/method for collating image and recording medium with image collation program recorded thereon | |
CN112686919B (en) | Object boundary line determining method and device, electronic equipment and storage medium | |
CN106326802A (en) | Two-dimensional code correction method and device and terminal device | |
US6707934B1 (en) | Apparatus and method for collating image | |
US6249603B1 (en) | Efficient search for a gray-level pattern in an image | |
JPH10334237A (en) | Fingerprint collation device | |
US8036433B1 (en) | Grid-based data input and authentication |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: FUJITSU LIMITED, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SEMBA, SATOSHI;FUJII, YUSAKU;ABIKO, YUKIHIRO;AND OTHERS;REEL/FRAME:016496/0106 Effective date: 20050215 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
CC | Certificate of correction | ||
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |